Breast Cancer Histopathological Image Classification Utilizing Convolutional Neural Network

Abstract

Breast cancer is a significant health concern prevailing in both developing and advanced countries where early and precise diagnosis of the disease receives significant attention from the scientific community. In this work, we proposed a deep learning approach using Convolutional Neural Network (CNN) to address the problem of classifying breast cancer using the public histopathological image dataset BreakHis. We propose a CNN model that takes input as preprocessed and augmented images from the available dataset and finally evaluate the classification performance of the model based on accuracy. The result shows that data preprocessing and augmentation significantly improve the performance of the model and help avoid overfitting due to class imbalance from the raw image set. The performance of our model also indicates the high capability of CNN in learning the representation that substantially improves the overall classifying accuracy of cancerous breast tissue.